Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    stock markets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    끔
    3.04
    ів
    2.95
    å
    2.72
    sız
    2.70
    ť
    2.68
     minist
    2.66
    sion
    2.65
    র্ঘট
    2.62
    ről
    2.59
     रोका
    2.58
    POSITIVE LOGITS
    iezan
    2.87
    brokers
    2.86
    ီ
    2.62
    2.62
    via
    2.59
     rafters
    2.59
    trek
    2.56
    те
    2.49
    EEEE
    2.49
     оригіналу
    2.48
    Act Density 0.029%

    No Known Activations